Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical references to time, particularly years and decades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    дян
    -0.58
     SSSR
    -0.58
    getDescriptor
    -0.57
    elry
    -0.57
     ExecuteAsync
    -0.57
    ()}>
    -0.56
    σιμοποι
    -0.55
     发表于
    -0.55
    WriteLiteral
    -0.51
    LabelTagHelper
    -0.50
    POSITIVE LOGITS
     half
    1.03
    half
    0.88
     ½
    0.79
    半
    0.77
    Half
    0.74
     HALF
    0.73
     Half
    0.73
    HALF
    0.72
    ½
    0.69
     mezzo
    0.69
    Act Density 0.189%

    No Known Activations